Model

Qwen3.8 2.4T A95B

Name: Qwen3.8 2.4T A95B
Brand: alibaba

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

15 providers · 16 listingsreleased Aug 12, 2026open weights

lowest input /M · NanoGPT

lowest output /M · NanoGPT

1.05M

context window

1.01M

max output

Compare providers (sorted by listed input price)

15 providers list Qwen3.8 2.4T A95B. The cheapest full-context option is Charm Hyper at $2/$6 per M. Requesty lists lower but caps context at 262K.

			Cache read /M	Cache write /M		Capabilities
NanoGPT qwen/qwen3.8-2.4t-a95b	$2	$6	$0.25	$2.50	991K	no reasoningtoolsstructuredvision	Aug 12, 2026
AIHubMix qwen3.8-2.4t-a95b	$2	$6	$0.5	—	262K	reasoningtoolsstructuredvision	Aug 12, 2026
Charm Hyper qwen3.8-2.4t-a95b	$2	$6	$0.25	—	1M	reasoningtoolsstructuredno vision	Aug 26, 2026
Requestyvariant qwen3.8-2.4T-A95B	$2	$6	$0.2	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026
Vercel AI Gateway alibaba/qwen3.8-2.4t-a95b	$2	$6	$0.25	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026
Fireworks AI accounts/fireworks/models/qwen3p8-2p4t-a95b	$2	$6	$0.25	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026
Deep Infra Qwen/Qwen3.8-2.4T-A95B	$2	$6	$0.2	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026
Kilo Gateway qwen/qwen3.8-2.4t-a95b	$2	$6	$0.25	$2.50	1M	reasoningtoolsstructuredno vision	Aug 12, 2026
OpenRouter qwen/qwen3.8-2.4t-a95b	$2	$6	$0.25	—	1.05M	reasoningtoolsstructuredno vision	Aug 12, 2026
RunInfra Inferact/Qwen3.8-2.4T-A95B-NVFP4	$2	$6	$0.2	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026
Eden AI qwen/qwen3.8-2.4t-a95b	$2	$6	$0.25	$2.50	1M	reasoningtoolsstructuredno vision	Aug 12, 2026
Requestyvariant qwen3.8-2.4T-A95B@eu	$2.50	$6	$0.63	—	1M	reasoningtoolsstructuredno vision	Aug 12, 2026
Hugging Face Qwen/Qwen3.8-2.4T-A95B	$2.50	$6.25	—	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026
Venice AI qwen-3-8-2-4t-a95b	$2.50	$7.50	$0.313	—	262K	reasoningtoolsstructuredno vision	Aug 13, 2026
Merge Gateway qwen/qwen3.8-2.4t-a95b	$2.50	$6.25	$0.5	—	262K	reasoningno toolsno structuredno vision	Aug 12, 2026
Cortecs qwen3.8-2.4t-a95b	$2.50	$6	$0.625	—	262K	reasoningtoolsstructuredno vision	Aug 12, 2026

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $2▲ 11.1%
Best output /M: $6▲ 11.1%
Provider coverage: 16; 11 at the start · 24 snapshots

Best input priceBest output priceAug 21, 2026 → Sep 14, 2026

Price badge

![Qwen3.8 2.4T A95B price](https://www.vaanalytics.in/badge/alibaba/qwen3.8-2.4t-a95b.svg)

https://www.vaanalytics.in/badge/alibaba/qwen3.8-2.4t-a95b.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →

contextvia kilo · Sep 9, 2026
- output: 262K → 131K tokens
contextvia openrouter · Sep 9, 2026
- output: 262K → 131K tokens
new modelvia fireworks-ai · Sep 5, 2026
repricedvia openrouter · Sep 3, 2026
- output: 131K → 262K tokens
- cache_read: $0.2 → $0.25
contextvia kilo · Sep 3, 2026
- context: 262K → 1M tokens
- output: 131K → 262K tokens
repricedvia openrouter · Sep 2, 2026
- output: 262K → 131K tokens
- cache_read: $0.25 → $0.2

Weights

Hugging Face

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.